Example usage for org.apache.lucene.search IndexSearcher IndexSearcher

List of usage examples for org.apache.lucene.search IndexSearcher IndexSearcher

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.search.*
  5. IndexSearcher
  6. IndexSearcher

Introduction

In this page you can find the example usage for org.apache.lucene.search IndexSearcher IndexSearcher.

Prototype

public IndexSearcher(IndexReaderContext context)

Source Link

Document

Creates a searcher searching the provided top-level IndexReaderContext .

Usage

From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java

License:Open Source License

/**
 * Returns a {@code List} of chromosome IDs for a project, specified by ID, where variations exist and satisfy a
 * specified query/*from  w w  w . j ava2 s.c o  m*/
 *
 * @param projectId an ID of a project, which index to query
 * @param query     a query to filter variations
 * @return a {@code List} of chromosome IDs
 * @throws IOException
 */
public List<Long> getChromosomeIdsWhereVariationsPresentFacet(long projectId, Query query) throws IOException {
    List<Long> chromosomeIds = new ArrayList<>();

    try (Directory index = fileManager.getIndexForProject(projectId);
            IndexReader reader = DirectoryReader.open(index)) {
        if (reader.numDocs() == 0) {
            return Collections.emptyList();
        }

        FacetsCollector facetsCollector = new FacetsCollector();
        IndexSearcher searcher = new IndexSearcher(reader);
        searcher.search(query, facetsCollector);

        Facets facets = new SortedSetDocValuesFacetCounts(new DefaultSortedSetDocValuesReaderState(reader,
                FeatureIndexFields.FACET_CHR_ID.getFieldName()), facetsCollector);
        FacetResult res = facets.getTopChildren(FACET_LIMIT, FeatureIndexFields.CHR_ID.getFieldName());
        if (res == null) {
            return Collections.emptyList();
        }

        for (LabelAndValue labelAndValue : res.labelValues) {
            chromosomeIds.add(Long.parseLong(labelAndValue.label));
        }
    }

    return chromosomeIds;
}

From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java

License:Open Source License

/**
 * Returns a {@code List} of chromosome IDs from specified files, where variations exist and satisfy a
 * specified query/*from   w ww.  j a  va 2 s  .  c om*/
 *
 * @param files a list of {@link FeatureFile}s to search chromosomes
 * @param query     a query to filter variations
 * @return a {@code List} of chromosome IDs
 * @throws IOException
 */
public List<Long> getChromosomeIdsWhereVariationsPresentFacet(List<? extends FeatureFile> files, Query query)
        throws IOException {
    if (CollectionUtils.isEmpty(files)) {
        return Collections.emptyList();
    }

    List<Long> chromosomeIds = new ArrayList<>();

    SimpleFSDirectory[] indexes = fileManager.getIndexesForFiles(files);

    try (MultiReader reader = openMultiReader(indexes)) {
        if (reader.numDocs() == 0) {
            return Collections.emptyList();
        }

        FacetsCollector facetsCollector = new FacetsCollector();
        IndexSearcher searcher = new IndexSearcher(reader);
        searcher.search(query, facetsCollector);

        Facets facets = new SortedSetDocValuesFacetCounts(new DefaultSortedSetDocValuesReaderState(reader,
                FeatureIndexFields.FACET_CHR_ID.getFieldName()), facetsCollector);
        FacetResult res = facets.getTopChildren(FACET_LIMIT, FeatureIndexFields.CHR_ID.getFieldName());
        if (res == null) {
            return Collections.emptyList();
        }

        for (LabelAndValue labelAndValue : res.labelValues) {
            chromosomeIds.add(Long.parseLong(labelAndValue.label));
        }
    } finally {
        closeIndexes(indexes);
    }

    return chromosomeIds;
}

From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java

License:Open Source License

/**
 * Searches gene IDs, affected by variations in specified VCF files in a specified project
 *
 * @param projectId an ID of a project to search genes
 * @param gene a prefix of a gene ID to search
 * @param vcfFileIds a {@code List} of IDs of VCF files in project to search for gene IDs
 * @return a {@code Set} of gene IDs, that are affected by some variations in specified VCf files
 * @throws IOException/* w ww  . j  a  v  a2 s.c om*/
 */
public Set<String> searchGenesInVcfFilesInProject(long projectId, String gene, List<Long> vcfFileIds)
        throws IOException {
    if (vcfFileIds == null || vcfFileIds.isEmpty()) {
        return Collections.emptySet();
    }

    BooleanQuery.Builder builder = new BooleanQuery.Builder();

    PrefixQuery geneIdPrefixQuery = new PrefixQuery(
            new Term(FeatureIndexFields.GENE_ID.getFieldName(), gene.toLowerCase()));
    PrefixQuery geneNamePrefixQuery = new PrefixQuery(
            new Term(FeatureIndexFields.GENE_NAME.getFieldName(), gene.toLowerCase()));
    BooleanQuery.Builder geneIdOrNameQuery = new BooleanQuery.Builder();
    geneIdOrNameQuery.add(geneIdPrefixQuery, BooleanClause.Occur.SHOULD);
    geneIdOrNameQuery.add(geneNamePrefixQuery, BooleanClause.Occur.SHOULD);

    builder.add(geneIdOrNameQuery.build(), BooleanClause.Occur.MUST);

    List<Term> terms = vcfFileIds.stream()
            .map(vcfFileId -> new Term(FeatureIndexFields.FILE_ID.getFieldName(), vcfFileId.toString()))
            .collect(Collectors.toList());
    TermsQuery termsQuery = new TermsQuery(terms);
    builder.add(termsQuery, BooleanClause.Occur.MUST);
    BooleanQuery query = builder.build();

    Set<String> geneIds;

    try (Directory index = fileManager.getIndexForProject(projectId);
            IndexReader reader = DirectoryReader.open(index)) {
        if (reader.numDocs() == 0) {
            return Collections.emptySet();
        }

        IndexSearcher searcher = new IndexSearcher(reader);
        final TopDocs docs = searcher.search(query, reader.numDocs());
        final ScoreDoc[] hits = docs.scoreDocs;

        geneIds = fetchGeneIds(hits, searcher);
    } catch (IOException e) {
        LOGGER.error(MessageHelper.getMessage(MessagesConstants.ERROR_FEATURE_INDEX_SEARCH_FAILED), e);
        return Collections.emptySet();
    }

    return geneIds;
}

From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java

License:Open Source License

public Set<String> searchGenesInVcfFiles(String gene, List<VcfFile> vcfFiles) throws IOException {
    if (CollectionUtils.isEmpty(vcfFiles)) {
        return Collections.emptySet();
    }//from  ww w .j  a  va  2  s  .  c om

    BooleanQuery.Builder builder = new BooleanQuery.Builder();

    PrefixQuery geneIdPrefixQuery = new PrefixQuery(
            new Term(FeatureIndexFields.GENE_ID.getFieldName(), gene.toLowerCase()));
    PrefixQuery geneNamePrefixQuery = new PrefixQuery(
            new Term(FeatureIndexFields.GENE_NAME.getFieldName(), gene.toLowerCase()));
    BooleanQuery.Builder geneIdOrNameQuery = new BooleanQuery.Builder();
    geneIdOrNameQuery.add(geneIdPrefixQuery, BooleanClause.Occur.SHOULD);
    geneIdOrNameQuery.add(geneNamePrefixQuery, BooleanClause.Occur.SHOULD);

    builder.add(geneIdOrNameQuery.build(), BooleanClause.Occur.MUST);
    BooleanQuery query = builder.build();

    Set<String> geneIds;

    SimpleFSDirectory[] indexes = fileManager.getIndexesForFiles(vcfFiles);

    try (MultiReader reader = openMultiReader(indexes)) {
        if (reader.numDocs() == 0) {
            return Collections.emptySet();
        }

        IndexSearcher searcher = new IndexSearcher(reader);
        final TopDocs docs = searcher.search(query, reader.numDocs());
        final ScoreDoc[] hits = docs.scoreDocs;

        geneIds = fetchGeneIds(hits, searcher);
    } catch (IOException e) {
        LOGGER.error(MessageHelper.getMessage(MessagesConstants.ERROR_FEATURE_INDEX_SEARCH_FAILED), e);
        return Collections.emptySet();
    }

    return geneIds;
}

From source file:com.epam.wilma.message.search.lucene.search.helper.IndexSearcherFactory.java

License:Open Source License

/**
 * Factory for creating new {@link IndexSearcher} instance using the given {@link IndexReader}.
 * @param indexReader is necessary to create {@link IndexSearcher}
 * @return with the new {@link IndexSearcher} instance
 *///from  w w  w .j ava2s.c  om
public IndexSearcher create(final IndexReader indexReader) {
    return new IndexSearcher(indexReader);
}

From source file:com.esri.gpt.catalog.lucene.LuceneIndexAdapter.java

License:Apache License

/**
 * Makes a searcher for catalog documents.
 * <p/>The searcher is created from the value returned by 
 * getCatalogIndexPath().//  w ww.  j  ava 2s  .  c  om
 * @return the writer
 * @throws CorruptIndexException if the index is corrupt 
 * @throws IOException if the directory cannot be read/written to, 
 *         or if it does not exist and create is false or if there is any 
 *         other low-level IO error
 */
public synchronized IndexSearcher newSearcher() throws CorruptIndexException, IOException {

    IndexSearcher searcher = null;
    if (!this.useSingleSearcher) {
        getLogger().finer("Opening Lucene IndexSearcher...");
        IndexReader reader = IndexReader.open(this.newDirectory(), true);
        searcher = new IndexSearcher(reader);
    } else {

        if (REFERENCED_SEARCHER == null) {
            REFERENCED_SEARCHER = new ReferencedSearcher(this.newDirectory());
            return REFERENCED_SEARCHER.get();
        } else {
            try {
                REFERENCED_SEARCHER.checkForReopen();
            } catch (InterruptedException e) {
                throw new IOException("Interrupted while opening single searcher.", e);
            }
            return REFERENCED_SEARCHER.get();
        }

        /*
        File fDir = new File(this.luceneConfig.getIndexLocation());
        String path = fDir.getCanonicalPath();
        synchronized (SEARCHERS) {
          searcher = SEARCHERS.get(path);
          if (searcher != null) {
            try {
              if (!searcher.getIndexReader().isCurrent()) {
                SEARCHERS.remove(path);
                searcher.getIndexReader().close();
                searcher.close();
                searcher = null;
              }
            } catch (AlreadyClosedException e) {
              SEARCHERS.remove(path);
              searcher = null;
            }
          }
          if (searcher == null) {
            IndexReader reader = IndexReader.open(this.newDirectory(),true);
            searcher = new IndexSearcher(reader);
            SEARCHERS.put(path,searcher);
          } 
        }
        */

    }
    return searcher;
}

From source file:com.esri.gpt.catalog.lucene.ReferencedSearcher.java

License:Apache License

/**
 * Constructs with a supplied directory.
 * @param dir the directory/*from   www .j  a v a2 s .c om*/
 */
public ReferencedSearcher(Directory dir) throws IOException {
    this.currentSearcher = new IndexSearcher(IndexReader.open(dir, true));
    this.warm(this.currentSearcher);
}

From source file:com.esri.gpt.catalog.lucene.ReferencedSearcher.java

License:Apache License

protected void checkForReopen() throws InterruptedException, IOException {
    this.onReopenBegin();
    try {/*w  w w. jav  a 2 s  .  com*/
        final IndexSearcher searcher = get();
        try {
            IndexReader newReader = this.currentSearcher.getIndexReader().reopen();
            if (newReader != this.currentSearcher.getIndexReader()) {
                IndexSearcher newSearcher = new IndexSearcher(newReader);
                this.warm(newSearcher);
                this.swap(newSearcher);
            }
        } catch (IOException e) {
            LogUtil.getLogger().log(Level.SEVERE, "Error during index re-open.", e);
        } finally {
            this.release(searcher);
        }
    } finally {
        onReopenEnd();
    }
}

From source file:com.esri.gpt.server.assertion.handler.AsnCommentHandler.java

License:Apache License

/**
 * Queries comments.//from w w w . j  a  v  a 2s. com
 * @param context the assertion operation context
 * @throws Exception if an exception occurs
 */
private void query(AsnContext context) throws Exception {

    // initialize
    AsnOperation operation = context.getOperation();
    AsnAssertionSet asnSet = operation.getAssertionSet();
    AsnValueType vType = asnSet.getValueType();
    String subject = operation.getSubject().getURN();
    String predicate = vType.getRdfPredicate();

    // build a query to match all occurrences of the subject/predicate pair
    BooleanQuery query = new BooleanQuery();
    Query qSubject = new TermQuery(new Term(AsnConstants.FIELD_RDF_SUBJECT, subject));
    Query qPredicate = new TermQuery(new Term(AsnConstants.FIELD_RDF_PREDICATE, predicate));
    query.add(qSubject, BooleanClause.Occur.MUST);
    query.add(qPredicate, BooleanClause.Occur.MUST);

    // sort on descending timestamp
    String tsField = AsnConstants.FIELD_SYS_TIMESTAMP;
    Sort sortOption = new Sort(new SortField(tsField, SortField.STRING, true));

    // determine the start and end positions
    int startRecord = context.getRequestOptions().getStartRecord() - 1;
    int maxRecords = context.getRequestOptions().getMaxRecords();
    if (startRecord < 0)
        startRecord = 0;
    int recordsPerPage = maxRecords;
    if (recordsPerPage <= 0)
        recordsPerPage = 1;
    int hitsToReturn = startRecord + recordsPerPage;
    int nextRecord = 0;
    int numDocs = 0;

    IndexReader reader = null;
    IndexSearcher searcher = null;
    try {

        // make the reader and searcher, execute the search
        reader = this.getIndexAdapter().makeIndexReader();
        searcher = new IndexSearcher(reader);
        TopDocs topDocs = searcher.search(query, null, hitsToReturn, sortOption);
        ScoreDoc[] scoreDocs = null;
        int totalHits = topDocs.totalHits;
        if (maxRecords > 0) {
            scoreDocs = topDocs.scoreDocs;
            if ((scoreDocs != null) && (scoreDocs.length) > 0) {
                numDocs = scoreDocs.length;
                if (totalHits > numDocs) {
                    nextRecord = numDocs + 1;
                }
            }
        }

        // root property for the response
        String rootSubject = subject;
        String roorPredicate = operation.getPredicate().getURN() + "response";
        AsnProperty rootProp = new AsnProperty(rootSubject, roorPredicate, null);

        // hit count and next record
        String queryPfx = asnSet.getURNPrefix() + ":query";
        rootProp.getChildren().add(new AsnProperty(null, queryPfx + ":hits", "" + totalHits));
        if (nextRecord > 0) {
            rootProp.getChildren().add(new AsnProperty(null, queryPfx + ":nextRecord", "" + nextRecord));
        }

        // canCreate capability for the active user
        String canCreatePred = asnSet.getURNPrefix() + ":activeUser:canCreate";
        String canCreateVal = "" + context.getAuthorizer().canCreate(context, asnSet.getAuthPolicy());
        rootProp.getChildren().add(new AsnProperty(null, canCreatePred, canCreateVal));

        // process the documents, generate the response
        AsnAssertionRenderer renderer = new AsnAssertionRenderer();
        for (int i = startRecord; i < numDocs; i++) {
            Document document = reader.document(scoreDocs[i].doc);
            Assertion assertion = asnSet.newAssertion(context, false);
            assertion.load(document);
            rootProp.getChildren().add(renderer.makeProperty(context, assertion));
        }
        context.getOperationResponse().generateResponse(context, rootProp.getChildren());

    } finally {
        this.getIndexAdapter().closeReader(reader);
        this.getIndexAdapter().closeSearcher(searcher);
    }

}

From source file:com.esri.gpt.server.assertion.handler.AsnRatingHandler.java

License:Apache License

/**
 * Summarizes the ratings for a resource.
 * @param context the assertion operation context
 * @throws Exception if an exception occurs
 *//* w  w  w  . java 2s .  com*/
private void query(AsnContext context) throws Exception {

    // initialize
    AsnOperation operation = context.getOperation();
    AsnAssertionSet asnSet = operation.getAssertionSet();
    AsnValueType vType = asnSet.getValueType();
    String subject = operation.getSubject().getURN();
    String predicate = vType.getRdfPredicate();
    String valueField = vType.getRdfValueField();
    String upValue = "urn:esri:geoportal:rating:value:up";
    String downValue = "urn:esri:geoportal:rating:value:down";

    IndexReader reader = null;
    IndexSearcher searcher = null;
    try {

        // make the reader and searcher
        reader = this.getIndexAdapter().makeIndexReader();
        searcher = new IndexSearcher(reader);

        // count up votes
        long nUp = this.getIndexAdapter().count(context, searcher, valueField, subject, predicate, upValue);

        // count down votes
        long nDown = this.getIndexAdapter().count(context, searcher, valueField, subject, predicate, downValue);

        // root property for the response
        String rootSubject = subject;
        String roorPredicate = operation.getPredicate().getURN() + "response";
        AsnProperty rootProp = new AsnProperty(rootSubject, roorPredicate, null);

        // up, down and total counts
        rootProp.getChildren().add(new AsnProperty(null, upValue + ":count", "" + nUp));
        rootProp.getChildren().add(new AsnProperty(null, downValue + ":count", "" + nDown));
        rootProp.getChildren().add(new AsnProperty(null, asnSet.getURNPrefix() + ":count", "" + (nUp + nDown)));

        // canCreate capability for the active user
        String canCreatePred = asnSet.getURNPrefix() + ":activeUser:canCreate";
        String canCreateVal = "" + context.getAuthorizer().canCreate(context, asnSet.getAuthPolicy());
        rootProp.getChildren().add(new AsnProperty(null, canCreatePred, canCreateVal));

        // user's previous rating
        Assertion previous = this.getIndexAdapter().loadPreviousUserAssertion(context, searcher);
        if (previous != null) {
            String prevSubj = Val.chkStr(previous.getSystemPart().getAssertionId());
            prevSubj = asnSet.getAssertionIdPrefix() + ":" + prevSubj;
            String predPred = asnSet.getURNPrefix() + ":activeUser:previousValue";
            String prevVal = previous.getRdfPart().getValue();
            rootProp.getChildren().add(new AsnProperty(prevSubj, predPred, prevVal));
        }

        // generate the response
        context.getOperationResponse().generateResponse(context, rootProp.getChildren());
    } finally {
        this.getIndexAdapter().closeReader(reader);
        this.getIndexAdapter().closeSearcher(searcher);
    }
}